Update app.py

app.py

@@ -1,77 +1,64 @@
 import gradio as gr
 from gtts import gTTS
-import os
 import tempfile
-from pydub import AudioSegment
-from pydub.playback import play
+import os
 import docx
+from pydub import AudioSegment
 
-# Global state
-line_index = 0
-all_lines = []
-
-# Function to extract text from an uploaded .docx file
+# Function to extract text from docx
 def extract_text_from_docx(file):
-    doc = docx.Document(file)
+    doc = docx.Document(file.name)
     return [para.text.strip() for para in doc.paragraphs if para.text.strip()]
 
-# Function to generate TTS and return audio path
-def generate_tts_audio(text, speed):
+# Function to convert Urdu text to speech
+def urdu_tts(text, speed):
     tts = gTTS(text=text, lang='ur')
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
-        tts.save(tmp_file.name)
-        audio_path = tmp_file.name
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp:
+        tts.save(tmp.name)
+        audio_path = tmp.name
 
-    # Adjust speed using pydub
+    # Change speed using pydub
     sound = AudioSegment.from_file(audio_path)
-    new_speed = max(0.5, min(speed, 2.0))  # clamp between 0.5x and 2.0x
-    altered_sound = sound._spawn(sound.raw_data, overrides={
-        "frame_rate": int(sound.frame_rate * new_speed)
-    }).set_frame_rate(sound.frame_rate)
+    sound = sound.speedup(playback_speed=speed)
+    final_path = audio_path.replace(".mp3", f"_x{speed}.mp3")
+    sound.export(final_path, format="mp3")
 
-    adjusted_path = audio_path.replace(".mp3", f"_x{speed}.mp3")
-    altered_sound.export(adjusted_path, format="mp3")
-    return adjusted_path
+    return final_path
 
-# Called when file is uploaded and "start" is clicked
+# Gradio stateful interface
 def start_reader(file, speed):
-    global line_index, all_lines
-    line_index = 0
-    all_lines = extract_text_from_docx(file)
-    if all_lines:
-        text = all_lines[0]
-        audio_path = generate_tts_audio(text, speed)
-        return text, audio_path, f"کل {len(all_lines)} لائنیں ملی ہیں۔", gr.update(visible=True)
-    else:
-        return "", None, "فائل میں کوئی اردو مواد نہیں ملا۔", gr.update(visible=False)
+    lines = extract_text_from_docx(file)
+    return lines, f"کل {len(lines)} لائنیں ملی ہیں۔", 0
 
-# Called when "next line" is clicked
-def next_line(speed):
-    global line_index, all_lines
-    if line_index + 1 < len(all_lines):
-        line_index += 1
-        text = all_lines[line_index]
-        audio_path = generate_tts_audio(text, speed)
-        return text, audio_path, f"لائن {line_index + 1} / {len(all_lines)}", gr.update(visible=True)
+def read_line(lines, line_idx, speed):
+    if line_idx < len(lines):
+        audio_file = urdu_tts(lines[line_idx], speed)
+        return lines[line_idx], audio_file, line_idx + 1
     else:
-        return "✅ تمام لائنیں مکمل ہو گئیں۔", None, f"کل {len(all_lines)} لائنیں مکمل ہو چکی ہیں۔", gr.update(visible=False)
+        return "📘 تمام لائنیں پڑھ لی گئیں!", None, line_idx
 
-# UI setup
-with gr.Blocks(title="📖 Urdu Line Reader") as demo:
-    gr.Markdown("## 📚 اردو فائل پڑھنے والا بوٹ")
-    gr.Markdown("`ایک Urdu .docx فائل اپلوڈ کریں، رفتار منتخب کریں، اور باری باری ہر لائن کو سنیں`")
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## 📖 اردو لائن بائی لائن ریڈر")
 
-    file = gr.File(label="📎 اردو فائل اپلوڈ کریں (.docx)", file_types=[".docx"])
-    speed = gr.Slider(0.5, 2.0, value=1.0, step=0.1, label="🔊 پڑھنے کی رفتار")
+    with gr.Row():
+        file_input = gr.File(label="📁 .docx فائل اپ لوڈ کریں", file_types=['.docx'])
+        speed_slider = gr.Slider(0.5, 2.0, 1.0, step=0.1, label="🔊 رفتار")
 
-    start_btn = gr.Button("فائل پڑھنا شروع کریں")
-    next_btn = gr.Button("اگلی لائن پڑھیں", visible=False)
+    start_button = gr.Button("🚀 فائل پڑھنا شروع کریں")
+    status = gr.Textbox(label="🔹 اسٹیٹس")
+    lines_state = gr.State()
+    index_state = gr.State()
+    
+    current_line = gr.Textbox(label="📌 موجودہ لائن", lines=2)
+    audio_output = gr.Audio(label="🎧 آڈیو")
 
-    text_display = gr.Textbox(label="📖 موجودہ لائن", interactive=False)
-    audio_output = gr.Audio(label="🔈 آڈیو", type="filepath", autoplay=True)
-    status = gr.Textbox(label="ℹ️ معلومات", interactive=False)
+    next_button = gr.Button("▶️ اگلی لائن پڑھیں")
 
-    start_btn.click(fn=start_reader, inputs=[file, speed], outputs=[text_display, audio_output, status, next_btn])
-    next_btn.click(fn=next_line, inputs=speed, outputs=[text_display, audio_output, status, next_btn])
+    start_button.click(fn=start_reader, inputs=[file_input, speed_slider],
+                       outputs=[lines_state, status, index_state])
+    
+    next_button.click(fn=read_line, inputs=[lines_state, index_state, speed_slider],
+                      outputs=[current_line, audio_output, index_state])
 
 demo.launch()